G

Nano Banana Pro (Gemini 3 Pro Image Preview)

Image/Videoby Google·Model page

Google's multimodal image generation and editing model with reasoning and a 65k-token context.

Max output

Most tokens the model can return in a single response.

33Ktokens
Reasoning
Reasoning-first model

Works through a step-by-step chain of thought before answering.

Share:

Design Arena

Design Arena ranks models on real-world front-end and design tasks — websites, UI components, data viz, SVG and more — through head-to-head human votes, scored as an ELO rating.
CategoryELOWin rateRank
Graphicdesign127765.9%#3
Image126662.2%#3
Imageediting126665.9%#2
Logo125461.0%#3

Pricing

per 1M tokens
Input$2 /1M
Output$12 /1M
Cache read$0.2 /1M
Cache write$0.375 /1M
Reasoning$12 /1M
Audio$2 /1M
Image$0.0000020
Web search$0.01

Model Description

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

Author
G
Google
Organization · ✓
google
Details
Downloads
Likes
AccessClosed Source
Context66K tokens
Input price$2 /1M
Output price$12 /1M
CreatedNov 20, 2025
Updated
View on Hugging Face
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Nano Banana Pro (Gemini 3 Pro Image Preview) — AI Model Details | Applied